Design of Morlet wavelet neural networks integrated with sequential quadratic programming to analyze the dynamics of Ebola virus disease
•Investigates the design of an integrated intelligent computing strategy in the framework of morlet wavelet neural networks.•Predicting solutions for Ebola virus disease.•Hybrid optimization algorithm with MWNNs and a genetic algorithm integrated with sequential quadratic programming.•Efficiency of...
Saved in:
| Published in: | Results in engineering Vol. 26; p. 105396 |
|---|---|
| Main Authors: | , , , , |
| Format: | Journal Article |
| Language: | English |
| Published: |
Elsevier B.V
01.06.2025
Elsevier |
| Subjects: | |
| ISSN: | 2590-1230, 2590-1230 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | •Investigates the design of an integrated intelligent computing strategy in the framework of morlet wavelet neural networks.•Predicting solutions for Ebola virus disease.•Hybrid optimization algorithm with MWNNs and a genetic algorithm integrated with sequential quadratic programming.•Efficiency of the proposed technique is confirmed by comparing results with a reference solution.•The accuracy, convergence, and stability of the proposed technique and prove that it can be applied to other non-linear disease models.
Ebola virus disease is caused by a virus that originates in flying foxes, or fruit bats. These bats may spread the virus to humans. The proposed model partitions the infected population into unaware and aware, and has a hospitalized compartment. Unlike previous models, which focused mostly on the general population, our model provides a more in-depth study of public health measures. Artificial neural networks (ANNs) are a highly effective approach for modeling intricate systems due to their ability to accurately approximate nonlinear functions. Their versatility and adaptability make them well-suited for addressing complex challenges in a variety of domains, such as epidemiology. The study aims to investigate the design of an integrated intelligent computing strategy in the framework of Morlet wavelet neural networks (MWNNs) for predicting solutions for an Ebola virus disease (EVD) model. For the investigation of this model, we use a hybrid optimization algorithm with MWNNs and a genetic algorithm (GA) integrated with sequential quadratic programming (SQP). The effectiveness of the developed MWNN-GA-SQP framework is thoroughly evaluated using a variety of error metrics such as mean absolute error (MAE), mean square error (MSE), and Theil’s inequality coefficient (TIC) to ensure a detailed and multidimensional performance assessment. A comparative evaluation with the conventional RK-4 numerical method as a reference solution is conducted with results illustrated through a variety of graphical tools, including histograms, box plots, and loss curves. The MWNN-GA-SQP framework's accuracy, consistency, and resilience are confirmed by thorough validation and verification against reference solutions, demonstrating its effectiveness in capturing the complex dynamics of epidemiological systems. Furthermore, the statistical analyses affirm the model's capability to precisely describe the nonlinear EVD model using an exponential incidence function, highlighting its potential as a powerful computational tool for analyzing infectious disease dynamics. |
|---|---|
| ISSN: | 2590-1230 2590-1230 |
| DOI: | 10.1016/j.rineng.2025.105396 |